Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to tree structures and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.19
     myſelf
    -1.19
     themſelves
    -1.16
     Monfieur
    -1.14
     Eſ
    -1.08
     greateſt
    -1.07
     ſeveral
    -1.07
     poffible
    -1.06
     auffi
    -1.06
    theless
    -1.06
    POSITIVE LOGITS
     tree
    1.78
     Tree
    1.76
     trees
    1.70
     TREE
    1.66
     Trees
    1.61
    Tree
    1.50
    Trees
    1.42
    tree
    1.40
    TREE
    1.36
     TREES
    1.26
    Act Density 0.043%

    No Known Activations